{"id":"gpt-6-astra","name":"GPT-6 Astra","vendor":"OpenAI","kind":"text","description":"GPT-6 Astra applies adjustable reasoning to technical problems that combine text and images, including mathematical arguments and engineering designs.","useCases":["Check the steps in a mathematical proof","Compare an engineering drawing with its written specification"],"technical":[{"label":"API model ID","value":"gpt-6-astra"},{"label":"Provider","value":"OpenAI"},{"label":"Modality","value":"Text"},{"label":"Input","value":"Chat messages"},{"label":"Output","value":"Text"},{"label":"Endpoint","value":"POST /v1/chat/completions"},{"label":"API constraints","value":"Function calling and sampling parameters are not available on Chat Completions for this model."}],"parameters":[{"name":"messages","type":"","description":""},{"name":"max_completion_tokens","type":"","description":""},{"name":"stream","type":"","description":""},{"name":"stream_options","type":"","description":""},{"name":"reasoning_effort","type":"","description":""},{"name":"response_format","type":"","description":""},{"name":"service_tier","type":"","description":""},{"name":"store","type":"","description":""},{"name":"safety_identifier","type":"","description":""},{"name":"prompt_cache_key","type":"","description":""},{"name":"user","type":"","description":""}],"pricing":{"currency":"USD","generated":"2026-11-21T02:23:44Z","notes":["A prompt over 272,000 tokens bills the whole request at the long-context rates."],"rates":[{"charge":"per 1M input tokens","options":"","price":12,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M input tokens","options":"prompts over 272,000 tokens","price":24,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M input tokens","options":"priority (service_tier: priority)","price":24,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M input tokens","options":"prompts over 272,000 tokens, priority (service_tier: priority)","price":48,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M input tokens","options":"flex (service_tier: flex)","price":6,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M input tokens","options":"prompts over 272,000 tokens, flex (service_tier: flex)","price":12,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M output tokens","options":"","price":60,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M output tokens","options":"prompts over 272,000 tokens","price":90,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M output tokens","options":"priority (service_tier: priority)","price":120,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M output tokens","options":"prompts over 272,000 tokens, priority (service_tier: priority)","price":180,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M output tokens","options":"flex (service_tier: flex)","price":30,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M output tokens","options":"prompts over 272,000 tokens, flex (service_tier: flex)","price":45,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M cached input tokens","options":"","price":1.2,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M cached input tokens","options":"prompts over 272,000 tokens","price":2.4,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M cached input tokens","options":"priority (service_tier: priority)","price":2.4,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M cached input tokens","options":"prompts over 272,000 tokens, priority (service_tier: priority)","price":4.8,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M cached input tokens","options":"flex (service_tier: flex)","price":0.6,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M cached input tokens","options":"prompts over 272,000 tokens, flex (service_tier: flex)","price":1.2,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M cache-write tokens","options":"","price":15,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M cache-write tokens","options":"prompts over 272,000 tokens","price":30,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M cache-write tokens","options":"priority (service_tier: priority)","price":30,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M cache-write tokens","options":"prompts over 272,000 tokens, priority (service_tier: priority)","price":60,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M cache-write tokens","options":"flex (service_tier: flex)","price":7.5,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M cache-write tokens","options":"prompts over 272,000 tokens, flex (service_tier: flex)","price":15,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1K responses that search the web","options":"","price":12,"from":null,"until":null,"note":null,"status":"active"}]},"links":{"page":"https://sociaro.com/models/gpt-6-astra","markdown":"https://sociaro.com/models/gpt-6-astra.md","json":"https://sociaro.com/models/gpt-6-astra.json","pricing":"https://sociaro.com/pricing?model=gpt-6-astra","docs":"https://docs.sociaro.com/models/gpt-6-astra/","playground":null},"examples":[]}